Analyze best power outputs (5s, 1min, 5min, 20min, 60min), estimate FTP, and compare with previous month
AI agents call get_power_curve to retrieve information from Strava Training MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing training data (power outputs, FTP estimates) from Strava, performing read-only computations on athlete metrics. No data is created, modified, deleted, or used to trigger external actions. The analysis is informational for training insights.
From the tool's definition Tool name 'get_power_curve' and description 'Analyze best power outputs... estimate FTP, and compare with previous month' indicate data retrieval and analysis only.
Attacks that exploit this kind of access
Analyze best power outputs (5s, 1min, 5min, 20min, 60min), estimate FTP, and compare with previous month. It is categorised as a Read tool in the Strava Training MCP MCP Server, which means it retrieves data without modifying state.
Register the Strava Training MCP server in PolicyLayer and add a rule for get_power_curve: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Strava Training MCP. Nothing to install.
get_power_curve is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_power_curve rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_power_curve. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_power_curve is provided by the Strava Training MCP server (ArjanLig/strava-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →